Imagebind: One Embedding Space To Bind Them All

Abstract

We present ImageBind, an approach to learn a joint embedding across six different modalities - images, text, audio, depth, thermal, and IMU data. We show that all combinations of paired data are not necessary to train such a joint embedding, and only image-paired data is sufficient to bind the modalities together. ImageBind can leverage recent large scale vision-language models, and extends their zero-shot capabilities to new modalities just by using their natural pairing with images. It enables novel emergent applications 'out-of-the-box' including cross-modal retrieval, composing modalities with arithmetic, cross-modal detection and generation. The emergent capabilities improve with the strength of the image encoder and we set a new state-of-the-art on emergent zero-shot recognition tasks across modalities, outperforming specialist supervised models. Finally, we show strong few-shot recognition results outperforming prior work, and that ImageBind serves as a new way to evaluate visio

Stats

• citations707
• S2 citations—
• github stars0
• HF likes0
• heat score21.38
• arxiv keygirdhar2023imagebind

Related papers

• From Latent To Engine Manifolds: Analyzing Imagebind's Multimodal Embedding Space (2024)0.00
• Efficient Discriminative Joint Encoders For Large Scale Vision-language Reranking (2025)0.00
• Image Search Using Multilingual Texts: A Cross-modal Learning Approach Between Image And Text (2019)0.00
• Learning Robust Visual-semantic Embeddings (2017)15.22
• ABC: Achieving Better Control Of Multimodal Embeddings Using Vlms (2025)0.00
• Textme: Bridging Unseen Modalities Through Text Descriptions (2026)0.00
• Deep Multimodal Image-text Embeddings For Automatic Cross-media Retrieval (2020)0.00
• Tri-modal Motion Retrieval By Learning A Joint Embedding Space (2024)7.81